diff --git a/dockerfiles/Dockerfile_cu130 b/dockerfiles/Dockerfile_cu130
new file mode 100644
index 000000000..2ae19d112
--- /dev/null
+++ b/dockerfiles/Dockerfile_cu130
@@ -0,0 +1,96 @@
+FROM nvidia/cuda:13.0.3-cudnn-devel-ubuntu24.04 AS base
+
+WORKDIR /app
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LANG=C.UTF-8
+ENV LC_ALL=C.UTF-8
+ENV LD_LIBRARY_PATH=/usr/local/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
+
+RUN apt-get update && apt-get install -y vim tmux zip unzip bzip2 wget git git-lfs build-essential libibverbs-dev ca-certificates \
+    curl iproute2 libsm6 libxext6 kmod ccache libnuma-dev libssl-dev flex bison libgtk-3-dev libpango1.0-dev \
+    libsoup2.4-dev libnice-dev libopus-dev libvpx-dev libx264-dev libsrtp2-dev libglib2.0-dev libdrm-dev libjpeg-dev libpng-dev \
+    && apt-get clean && rm -rf /var/lib/apt/lists/* && git lfs install
+
+RUN curl -fsSL -v -o /app/miniconda.sh -O  "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh"
+RUN chmod +x /app/miniconda.sh && \
+    bash /app/miniconda.sh -b -p /app/miniconda && \
+    rm /app/miniconda.sh && \
+    /app/miniconda/bin/conda install python=3.11 -y && \
+    /app/miniconda/bin/conda clean -ya
+ENV PATH="/app/miniconda/bin:$PATH"
+
+RUN conda install conda-forge::ffmpeg=8.0.0 -y && conda clean -all -y
+
+RUN pip install --no-cache-dir packaging ninja cmake scikit-build-core uv meson ruff pre-commit fastapi uvicorn requests -U
+
+RUN pip install torch==2.11.0 torchvision==0.26.0 torchaudio==2.11.0 --index-url https://download.pytorch.org/whl/cu130
+
+RUN git clone https://github.com/vllm-project/vllm.git && cd vllm \
+    && python use_existing_torch.py && pip install --no-cache-dir -r requirements/build/cuda.txt \
+    && pip install --no-cache-dir --no-build-isolation -v -e .
+
+RUN git clone https://github.com/sgl-project/sglang.git && cd sglang/sgl-kernel \
+    && make build && make clean
+
+RUN pip install --no-cache-dir diffusers transformers tokenizers accelerate safetensors opencv-python numpy imageio \
+    imageio-ffmpeg einops loguru qtorch ftfy av decord matplotlib debugpy soundfile jsonschema pymongo modelscope \
+    Pillow peft omegaconf mooncake-transfer-engine torchao scipy bson aio-pika asyncpg>=0.27.0 aioboto3>=12.0.0 \
+    PyJWT alibabacloud_dypnsapi20170525==1.2.2 redis==6.4.0 tos zmq
+
+RUN git clone https://github.com/Dao-AILab/flash-attention.git --recursive
+
+RUN cd flash-attention && python setup.py install && rm -rf build
+
+RUN cd flash-attention/hopper && python setup.py install && rm -rf build
+
+RUN cd flash-attention && pip install -e "flash_attn/cute[dev,cu13]"
+
+RUN git clone https://github.com/ModelTC/SageAttention.git --depth 1
+
+RUN cd SageAttention && CUDA_ARCHITECTURES="8.0,8.6,8.9,9.0,12.0" EXT_PARALLEL=4 NVCC_APPEND_FLAGS="--threads 8" MAX_JOBS=32 pip install --no-cache-dir --no-build-isolation -v -e .
+
+RUN git clone https://github.com/ModelTC/SageAttention-1104.git --depth 1
+
+RUN cd SageAttention-1104/sageattention3_blackwell && python setup.py install && rm -rf build
+
+RUN git clone https://github.com/SandAI-org/MagiAttention.git --recursive
+
+RUN cd MagiAttention && MAGI_ATTENTION_BUILD_COMPUTE_CAPABILITY="90,100" pip install --no-cache-dir --no-build-isolation -v -e .
+
+COPY lightx2v_kernel /app/lightx2v_kernel
+
+RUN git clone https://github.com/NVIDIA/cutlass.git --depth 1 && cd /app/lightx2v_kernel && MAX_JOBS=32 && CMAKE_BUILD_PARALLEL_LEVEL=4 \
+    uv build --wheel \
+        -Cbuild-dir=build . \
+        -Ccmake.define.CUTLASS_PATH=/app/cutlass \
+        --verbose \
+        --color=always \
+        --no-build-isolation \
+    && pip install dist/*whl --force-reinstall --no-deps \
+    && rm -rf /app/lightx2v_kernel && rm -rf /app/cutlass
+
+RUN git clone --depth 1 https://github.com/linux-rdma/rdma-core.git && \
+    cd rdma-core/ && \
+    mkdir build-ibv57 && \
+    cd build-ibv57 && \
+    cmake .. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr/local -DNO_MAN_PAGES=1 && \
+    make -j"$(nproc)" && \
+    make install && \
+    ldconfig
+
+# for base docker
+RUN git clone https://github.com/ModelTC/q8_kernels.git --depth 1
+RUN cd q8_kernels && git submodule init && git submodule update && python setup.py install && rm -rf build
+
+RUN git clone https://github.com/ModelTC/SpargeAttn-Fix.git --depth 1
+RUN cd SpargeAttn-Fix && TORCH_CUDA_ARCH_LIST="8.0;8.6;8.9;9.0" pip install --no-cache-dir --no-build-isolation -v -e .
+
+# for 5090 docker
+# RUN git clone https://github.com/ModelTC/LTX-Video-Q8-Kernels.git --depth 1
+# RUN cd LTX-Video-Q8-Kernels && git submodule init && git submodule update && python setup.py install && rm -rf build
+
+# RUN git clone https://github.com/ModelTC/SpargeAttn.git --depth 1
+# RUN cd SpargeAttn && TORCH_CUDA_ARCH_LIST="12.0" pip install --no-cache-dir --no-build-isolation -v -e .
+
+WORKDIR /workspace